Speech enhancement algorithm based on MMSE spectral subtraction with Laplacian distribution

doi:10.11772/j.issn.1001-9081.2019071152

Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (3): 878-882.DOI: 10.11772/j.issn.1001-9081.2019071152

• Virtual reality and multimedia computing • Previous Articles Next Articles

Speech enhancement algorithm based on MMSE spectral subtraction with Laplacian distribution

WANG Yongbiao^1,2, ZHANG Wenxi^1,2, WANG Yahui¹, KONG Xinxin¹, LYU Tong^1,2

1. Key Laboratory of Computation Optical Imaging Technology, Academy of Opto-Electronics, Chinese Academy of Sciences, Beijing 100094, China;
2. School of Electronic, Electrical and Communication, University of Chinese Academy of Sciences, Beijing 100049, China

Received:2019-07-03 Revised:2019-08-30 Online:2020-03-10 Published:2019-09-19
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61605217).

拉普拉斯分布下的MMSE谱减语音增强算法

王永彪^1,2, 张文喜^1,2, 王亚慧¹, 孔新新¹, 吕彤^1,2

1. 中国科学院光电研究院计算光学成像技术重点实验室, 北京 100094;
2. 中国科学院大学电子电气与通信工程学院, 北京 100049

通讯作者: 张文喜
作者简介:王永彪(1995-),男,山东德州人,硕士研究生,主要研究方向:语音信号处理;张文喜(1979-),男,安徽宿州人,研究员,博士,主要研究方向:激光测量、相干成像;王亚慧(1990-),女,山东菏泽人,博士研究生,主要研究方向:语音信号处理;孔新新(1988-),男,山东曲阜人,博士研究生,主要研究方向:光学精密测量;吕彤(1995-),女,北京人,硕士研究生,主要研究方向:光学精密测量。
基金资助:
国家自然科学基金资助项目（61605217）。

Abstract

Abstract: A Minimum Mean Square Error (MMSE) speech enhancement algorithm based on Laplacian distribution was proposed to solve the problem of noise residual and speech distortion of speech enhanced by the spectral subtraction algorithm based on Gaussian distribution. Firstly, the original noisy speech signal was framed and windowed, and the Fourier transform was performed on the signal of each processed frame to obtain the Discrete-time Fourier Transform (DFT) coefficient of short-term speech. Secondly, the noisy frame detection was performed to update the noise estimation by calculating the logarithmic spectrum energy and spectral flatness of each frame. Thirdly, based on the assumption of Laplace distribution of speech DFT coefficient, the optimal spectral subtraction coefficient was derived under the MMSE criterion, and the spectral subtraction with the obtained coefficient was performed to obtain the enhanced signal spectrum. Finally, the enhanced signal spectrum was subjected to inverse Fourier transform and framing to obtain the enhanced speech. The experimental results show that the Signal-to-Noise Ratio (SNR) of the speech enhanced by the proposed algorithm is increased by 4.3 dB on average, and has 2 dB improvement compared with that of the speech enhanced by the over-subtraction method. In the term of Perceptual Evaluation of Speech Quality (PESQ) score, compared with that of over-subtraction method, the average score of the proposed algorithm has a 10% improvement. The proposed algorithm has better noise suppression and less speech distortion, and has a significant improvement in SNR and PESQ evaluation standards.

Key words: speech enhancement, spectrum subtraction, Minimum Mean Square Error (MMSE), short-term logarithmic spectrum, spectral flatness

摘要： 针对基于高斯分布的谱减语音增强算法，增强语音出现噪声残留和语音失真的问题，提出了基于拉普拉斯分布的最小均方误差（MMSE）谱减算法。首先，对原始带噪语音信号进行分帧、加窗处理，并对处理后每帧的信号进行傅里叶变换，得到短时语音的离散傅里叶变换（DFT）系数；然后，通过计算每一帧的对数谱能量及谱平坦度，进行噪声帧检测，更新噪声估计；其次，基于语音DFT系数服从拉普拉斯分布的假设，在最小均方误差准则下，求解最佳谱减系数，使用该系数进行谱减，得到增强信号谱；最后，对增强信号谱进行傅里叶逆变换、组帧，得到增强语音。实验结果表明，使用所提算法增强的语音信噪比（SNR）平均提高了4.3 dB，与过减法相比，有2 dB的提升；在语音质量感知评估（PESQ）得分方面，与过减法相比，所提算法平均得分有10%的提高。该算法有更好的噪声抑制能力和较小的语音失真，在SNR和PESQ评价标准上有较大提升。

关键词: 语音增强, 谱减, 最小均方误差, 短时对数谱, 谱平坦度

CLC Number:

TP391.9

WANG Yongbiao, ZHANG Wenxi, WANG Yahui, KONG Xinxin, LYU Tong. Speech enhancement algorithm based on MMSE spectral subtraction with Laplacian distribution[J]. Journal of Computer Applications, 2020, 40(3): 878-882.

王永彪, 张文喜, 王亚慧, 孔新新, 吕彤. 拉普拉斯分布下的MMSE谱减语音增强算法[J]. 计算机应用, 2020, 40(3): 878-882.

References

[1] BOLL S. Suppression of acoustic noise in speech using spectral subtraction[J]. IEEE Transactions on Acoustics,Speech,and Signal Processing,1979,27(2):113-120.
[2] MCAULAY R,MALPASS M. Speech enhancement using a soft-decision noise suppression filter[J]. IEEE Transactions on Acoustics, Speech,and Signal Processing,1980,28(2):137-145.
[3] EPHRAIM Y,VAN TREES H L. Signal subspace approach for speech enhancement[J]. IEEE Transactions on Speech Audio Processing,1995,3(4):251-266.
[4] 徐勇. 基于深层神经网络的语音增强方法研究[D]. 合肥:中国科学技术大学,2015:67-79. (XU Y. Research on deep neural network based speech enhancement[D]. Hefei:University of Science and Technology of China,2015:67-79.)
[5] 隋璐瑛, 张雄伟, 黄建军, 等. 一种基于非负矩阵分解的语音增强算法[J]. 军事通信技术,2012,33(1):19-22.(SUI L Y, ZHANG X W,HUANG J J,et al. Speech enhancement based on nonnegative matrix factorization[J]. Journal of Military Communications Technology,2012,33(1):19-22.)
[6] BEROUTI M,SCHWARTZ R,MAKHOUL J. Enhancement of speech corrupted by acoustic noise[C]//Proceedings of the 1979 IEEE International Conference on Acoustics,Speech,and Signal Processing. Piscataway:IEEE,1979:208-211.
[7] LOCKWOOD P,BOUDY J,BLANCHET M. Non-linear Spectral Subtraction(NSS)and hidden Markov models for robust speech recognition in car noise environments[C]//Proceedings of the 1992 IEEE International Conference on Acoustics,Speech,and Signal Processing. Piscataway:IEEE,1992:265-268.
[8] MARTIN R. Speech enhancement using MMSE short time spectral estimation with gamma distributed speech priors[C]//Proceedings of the 2002 IEEE International Conference on Acoustics,Speech, and Signal Processing. Piscataway:IEEE,2002:I-253-I-256.
[9] EPHRAIM Y,MALAH D. Speech enhancement using a minimum mean-square error log-spectral amplitude estimator[J]. IEEE Transactions on Acoustics,Speech,and Signal Processing,1985,33(2):443-445.
[10] LOIZOU P C. 语音增强理论与实践[M]. 高毅, 肖莉, 邓芳, 等, 译. 成都:电子科技大学出版社,2012:88-92.(LOIZOU P C. Speech Enhancement Theory and Practice[M]. GAO Y,XIAO L,DENG F,et al,translated. Chengdu:University of Electronic Science and Technology of China Press,2012:88-92.)
[11] QUATIERI T F,DUNN R B. Speech enhancement based on auditory spectral change[C]//Proceedings of the 2002 IEEE International Conference on Acoustics,Speech,and Signal Processing. Piscataway:IEEE,2002:I-257-I-260.
[12] SIM B L,TONG Y C,CHANG J S,et al. A parametric formulation of the generalized spectral subtraction method[J]. IEEE Transactions on Speech and Audio Processing, 1998, 6(4):328-337.
[13] PAPOULIS A,PILLAI S U. Probability,Random Variables,and Stochastic Processes[M]. Pennsylvania Plaza,NY:McGraw-Hill Education,2002:207-210.
[14] CHEN B,LOIZOU P C. Speech enhancement using a MMSE short time spectral amplitude estimator with Laplacian speech modeling[C]//Proceedings of the 2005 IEEE International Conference on Acoustics,Speech,and Signal Processing,Piscataway:IEEE, 2005:I/1097-I/1100.
[15] 王让定, 柴佩琪. 一个基于谱熵的语音端点检测改进方法[J]. 信息与控制,2004,33(1):77-81. (WANG R D,CHAI P Q. An improved speech endpoint detection method based on spectral entropy[J]. Information and Control,2004,33(1):77-81.)
[16] RIX A W,BEERENDS J G,KIM D S,et al. Objective assessment of speech and audio quality-technology and applications[J]. IEEE Transactions on Audio Speech,and Language Processing, 2006,14(6):1890-1901.

Speech enhancement algorithm based on MMSE spectral subtraction with Laplacian distribution

拉普拉斯分布下的MMSE谱减语音增强算法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	LONG Chao, ZENG Qingning, LUO Ying. Small-array speech enhancement based on noise cancellation and beamforming [J]. Journal of Computer Applications, 2020, 40(8): 2386-2391.
[2]	WU Qinghe, WU Haifeng, SHEN Yong, ZENG Yu. Speech enhancement using multi-microphone state space model under industrial noise environment [J]. Journal of Computer Applications, 2020, 40(5): 1476-1482.
[3]	LI Yansheng, LIU Yuan, ZHANG Yi. Reconstructed NMF single channel speech enhancement algorithm based on perceptual masking [J]. Journal of Computer Applications, 2019, 39(3): 894-898.
[4]	GE Wanying, ZHANG Tianqi. Monaural speech enhancement algorithm based on mask estimation and optimization [J]. Journal of Computer Applications, 2019, 39(10): 3065-3070.
[5]	JIANG Maosong, WANG Dongxia, NIU Fanglin, CAO Yudong. Speech enhancement method based on sparsity-regularized non-negative matrix factorization [J]. Journal of Computer Applications, 2018, 38(4): 1176-1180.
[6]	XU Wenchao, WANG Guangyan, CHEN Lei. Speech enhancement algorithm based on improved variable-step LMS algorithm in cochlear implant [J]. Journal of Computer Applications, 2017, 37(4): 1212-1216.
[7]	LIU Jingang, ZHOU Yi, MA Yongbao, LIU Hongqing. Estimation algorithm of switching speech power spectrum for automatic speech recognition system [J]. Journal of Computer Applications, 2016, 36(12): 3369-3373.
[8]	MA Jinlong, ZENG Qingning, HU Dan, LONG Chao, XIE Xianming. Speech enhancement algorithm based on microphone array under multiple noise environments [J]. Journal of Computer Applications, 2015, 35(8): 2341-2344.
[9]	LIU Yan, NI Wanshun. Speech enhancement based on bionic wavelet transform of subband spectrum entropy [J]. Journal of Computer Applications, 2015, 35(3): 868-871.
[10]	CAI Yu HAO Chengpeng HOU Caohuan. Speech enhancement using subband spectral-subtraction [J]. Journal of Computer Applications, 2014, 34(2): 567-571.
[11]	WANG yulinYulin TIAN Xuelong GAO Xueli. Modified speech enhancement algorithm based on de-correlation variable step size [J]. Journal of Computer Applications, 2013, 33(06): 1746-1749.
[12]	LI Shi-ping WANG Long. Improved sphere decoding detection algorithm combined with minimum mean square error [J]. Journal of Computer Applications, 2012, 32(02): 385-387.
[13]	QI Mei-juan WU Yu-cheng. Correlation rotation precoding algorithm based on criterion of minimum mean square error [J]. Journal of Computer Applications, 2012, 32(01): 147-149.
[14]	HE Zhi-yong ZHU Zhong-kui. Removal of impulsive noise based on Kalman filtering for speech enhancement [J]. Journal of Computer Applications, 2011, 31(12): 3441-3445.
[15]	. Adaptive threshold speech de-noising based on Bark scale wavelet package [J]. Journal of Computer Applications, 2010, 30(11): 3111-3114.